GenAI Lead: Enterprise RAG & API Architect

9NEXUS Limited; United States; À distance; USD 140 000 - 200 000; Plein temps

Résumé du poste

9nexus seeks a GenAI Engineer to design, develop, and deploy enterprise-grade AI applications using LLMs. You will build REST APIs with Python and FastAPI, and integrate AI services with databases and external APIs.

You will implement prompt engineering, evaluation, guardrails, and production-ready architectures, while working with vector databases (Pinecone, Weaviate, Chroma, FAISS, Milvus) and cloud environments (Azure/AWS/GCP) for scalable deployments.

Qualifications

• Must have hands-on Python development experience.
• Hands-on API development with FastAPI.
• Proven experience implementing LLMs (GPT, Claude, Gemini, Llama, etc.).
• Experience building end-to-end RAG solutions using embeddings and vector databases.

Responsabilités

• Design, develop, and deploy enterprise-grade GenAI applications using LLMs.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines using vector databases and embeddings.
• Develop agent-based workflows using frameworks such as LangChain, LangGraph, CrewAI, or AutoGen.
• Build REST APIs and AI services using Python and FastAPI.
• Implement prompt engineering, model evaluation, guardrails, and response optimization techniques.
• Integrate LLMs with enterprise applications, databases, and external APIs.
• Design scalable AI architectures and support production deployments.

Connaissances

Python development

FastAPI API development

LLMs integration

RAG pipelines

Agent frameworks (LangChain, LangGraph

Prompt engineering

Vector databases

Cloud deployment

Description du poste

9nexus seeks a GenAI Engineer to design, develop, and deploy enterprise-grade AI applications using LLMs. You will build REST APIs with Python and FastAPI, and integrate AI services with databases and external APIs.

You will implement prompt engineering, evaluation, guardrails, and production-ready architectures, while working with vector databases (Pinecone, Weaviate, Chroma, FAISS, Milvus) and cloud environments (Azure/AWS/GCP) for scalable deployments.